NeRF
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik et al.
2021 · Communications of the ACM · 5,967 citations
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a fully connected (nonconvolutional) deep network, whose input is a single continuous 5D coordinate (spatial location ( x , y , z ) and viewing direction ( θ, ϕ )) and whose output is the volume density and view-dependent emitted radiance at that spatial location. We synthesize views by querying 5D coordinates along camera rays and use classic volume r…
Explore this paper's citation graph on Constellation.